Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1387
    Prev
    Next
    INDEX
    Explanations

    communauté active, informations existantes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Các
    1.15
     paparazzi
    1.08
    ༨
    1.05
     Una
    1.04
     commissioned
    1.03
     Петер
    1.03
     Một
    1.00
    ༠
    1.00
     các
    1.00
     አንድ
    0.99
    POSITIVE LOGITS
     d
    1.10
     du
    0.96
     ainsi
    0.93
     permettant
    0.87
     à
    0.86
     aussi
    0.86
     également
    0.82
     étant
    0.81
     de
    0.80
     et
    0.79
    Activations Density 0.044%

    No Known Activations